Aligning LLM Agents by Learning Latent Preference from User Edits

• URL: http://arxiv.org/abs/2404.15269v3
• Date: Sat, 23 Nov 2024 16:19:03 GMT
• Title: Aligning LLM Agents by Learning Latent Preference from User Edits
• Authors: Ge Gao, Alexey Taymanov, Eduardo Salinas, Paul Mineiro, Dipendra Misra,
• Abstract summary: We study interactive learning of language agents based on user edits made to the agent's output. We propose a learning framework, PRELUDE, that infers a description of the user's latent preference based on historic edit data. We introduce two interactive environments -- summarization and email writing, and use a GPT-4 simulated user for evaluation.
• Score: 23.235995078727658
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study interactive learning of LLM-based language agents based on user edits made to the agent's output. In a typical setting such as writing assistants, the user interacts with a language agent to generate a response given a context, and may optionally edit the agent response to personalize it based on their latent preference, in addition to improving the correctness. The edit feedback is naturally generated, making it a suitable candidate for improving the agent's alignment with the user's preference, and for reducing the cost of user edits over time. We propose a learning framework, PRELUDE that infers a description of the user's latent preference based on historic edit data. The inferred user preference descriptions are used to define prompts for generating responses in the future. This avoids fine-tuning the agent, which is costly, challenging to scale with the number of users, and may even degrade its performance on other tasks. Furthermore, learning descriptive preference improves interpretability, allowing the user to view and modify the learned preference. However, user preference can be complex, subtle, and vary based on context, making it challenging to learn. To address this, we propose a simple yet effective algorithm named CIPHER that leverages the LLM to infer the user preference for a given context based on user edits. In the future, CIPHER retrieves inferred preferences from the k-closest contexts in the history, and forms an aggregate preference for response generation. We introduce two interactive environments -- summarization and email writing, and use a GPT-4 simulated user for evaluation. On both tasks, CIPHER outperforms several baselines by achieving the lowest edit distance cost while only having a small overhead in LLM query cost. Our analysis reports that user preferences learned by CIPHER show significant similarity to the ground truth latent preferences.

Related papers

• Learning Pluralistic User Preferences through Reinforcement Learning Fine-tuned Summaries [13.187789731783095]
  We present a novel framework that learns text-based summaries of each user's preferences, characteristics, and past conversations.<n>These summaries condition the reward model, enabling it to make personalized predictions about the types of responses valued by each user.<n>We show that our method is robust to new users and diverse conversation topics.
  arXiv  Detail & Related papers  (2025-07-17T23:48:51Z)
• Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale [51.9706400130481]
  Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks. PERSONAMEM features curated user profiles with over 180 simulated user-LLM interaction histories. We evaluate LLM chatbots' ability to identify the most suitable response according to the current state of the user's profile.
  arXiv  Detail & Related papers  (2025-04-19T08:16:10Z)
• FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users [111.56469697145519]
  We propose Few-Shot Preference Optimization, which reframes reward modeling as a meta-learning problem. Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them. We generate over 1M synthetic personalized preferences using publicly available LLMs. We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study.
  arXiv  Detail & Related papers  (2025-02-26T17:08:46Z)
• UQABench: Evaluating User Embedding for Prompting LLMs in Personalized Question Answering [39.79275025010785]
  name is a benchmark designed to evaluate the effectiveness of user embeddings in prompting large language models for personalization. We conduct extensive experiments on various state-of-the-art methods for modeling user embeddings.
  arXiv  Detail & Related papers  (2025-02-26T14:34:00Z)
• ULMRec: User-centric Large Language Model for Sequential Recommendation [16.494996929730927]
  We propose ULMRec, a framework that integrates user personalized preferences into Large Language Models. Extensive experiments on two public datasets demonstrate that ULMRec significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2024-12-07T05:37:00Z)
• Unveiling User Preferences: A Knowledge Graph and LLM-Driven Approach for Conversational Recommendation [55.5687800992432]
  We propose a plug-and-play framework that synergizes Large Language Models (LLMs) and Knowledge Graphs (KGs) to unveil user preferences. This enables the LLM to transform KG entities into concise natural language descriptions, allowing them to comprehend domain-specific knowledge.
  arXiv  Detail & Related papers  (2024-11-16T11:47:21Z)
• Optimizing Data Delivery: Insights from User Preferences on Visuals, Tables, and Text [59.68239795065175]
  We conduct a user study where users are shown a question and asked what they would prefer to see. We use the data to establish that a user's personal traits does influence the data outputs that they prefer.
  arXiv  Detail & Related papers  (2024-11-12T00:24:31Z)
• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align'' We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures. For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• PersonalLLM: Tailoring LLMs to Individual Preferences [11.717169516971856]
  We present a public benchmark, PersonalLLM, focusing on adapting LLMs to provide maximal benefits for a particular user. We curate open-ended prompts paired with many high-quality answers over which users would be expected to display heterogeneous latent preferences. Our dataset and generated personalities offer an innovative testbed for developing personalization algorithms.
  arXiv  Detail & Related papers  (2024-09-30T13:55:42Z)
• Reinforced Prompt Personalization for Recommendation with Large Language Models [24.360796133889156]
  We introduce the concept of instance-wise prompting, aiming at personalizing discrete prompts for individual users. To improve efficiency and quality, RPP personalizes prompts at the sentence level rather than searching in the vast vocabulary word-by-word.
  arXiv  Detail & Related papers  (2024-07-24T09:24:49Z)
• Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search [9.243535345193711]
  Our method uses large language models to guide a single human worker in generating personalized dialogues. LAPS can collect large-scale, human-written, multi-session, and multi-domain conversations. Our results show that responses generated explicitly using extracted preferences better match user's actual preferences.
  arXiv  Detail & Related papers  (2024-05-06T13:53:03Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs. Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• User-LLM: Efficient LLM Contextualization with User Embeddings [23.226164112909643]
  User-LLM is a novel framework that leverages user embeddings to directly contextualize large language models with user history interactions. Our approach achieves significant efficiency gains by representing user timelines directly as embeddings, leading to substantial inference speedups of up to 78.1X.
  arXiv  Detail & Related papers  (2024-02-21T08:03:27Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• Personalized Language Modeling from Personalized Human Feedback [49.344833339240566]
  Reinforcement Learning from Human Feedback (RLHF) is commonly used to fine-tune large language models to better align with human preferences. In this work, we aim to address this problem by developing methods for building personalized language models.
  arXiv  Detail & Related papers  (2024-02-06T04:18:58Z)
• Interpreting User Requests in the Context of Natural Language Standing Instructions [89.12540932734476]
  We develop NLSI, a language-to-program dataset consisting of over 2.4K dialogues spanning 17 domains. A key challenge in NLSI is to identify which subset of the standing instructions is applicable to a given dialogue.
  arXiv  Detail & Related papers  (2023-11-16T11:19:26Z)
• Eliciting Human Preferences with Language Models [56.68637202313052]
  Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. We propose to use *LMs themselves* to guide the task specification process. We study GATE in three domains: email validation, content recommendation, and moral reasoning.
  arXiv  Detail & Related papers  (2023-10-17T21:11:21Z)
• Factual and Personalized Recommendations using Language Models and Reinforcement Learning [38.96462170594542]
  We develop a comPelling, Precise, Personalized, Preference-relevant language model (P4LM) P4LM recommends items to users while putting emphasis on explaining item characteristics and their relevance. We develop a joint reward function that measures precision, appeal, and personalization.
  arXiv  Detail & Related papers  (2023-10-09T21:58:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.